Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    opposite oforvs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     october
    0.42
     administrar
    0.41
     kindergarten
    0.40
     universitario
    0.40
    excludeFolder
    0.39
    <unused24>
    0.39
     Nonprofit
    0.39
     administrations
    0.38
    ంటర్
    0.38
    ❗️
    0.38
    POSITIVE LOGITS
     similaires
    0.44
     similarly
    0.43
     իր
    0.42
     timeless
    0.41
     একইভাবে
    0.41
     instilled
    0.40
    czek
    0.39
    gi
    0.39
     Bryce
    0.39
     imparted
    0.39
    Act Density 0.005%

    No Known Activations